Extract the 44-digit chave de acesso, CNPJ, CFOP and NCM codes, ICMS, and line items from a Brazilian NF-e (Nota Fiscal Eletronica) PDF.
The full guide: Chave de acesso and ICMS from an NF-e or DANFE
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
It is the authorized Brazilian electronic invoice (Nota Fiscal Eletronica), cleared by SEFAZ under layout 4.00. The extractor reads the 44-digit access key (chave de acesso) used to validate and track the document at SEFAZ, the document number and series, the document model (55 for NF-e, 65 for the consumer NFC-e), the layout version, and the environment type (1 production, 2 homologation).
The supplier and buyer legal name, tax ID (CNPJ, 14 digits, or CPF), and state registration (Inscricao Estadual), the issuer tax regime (1 Simples Nacional, 3 Regime Normal) and the buyer IE indicator, the issuer state (UF) IBGE code and the tax-fact municipality IBGE code, and the operation nature (such as VENDA or DEVOLUCAO) and operation direction (0 inbound, 1 outbound).
Yes. The line items table returns each product with its product code, barcode (GTIN), description, NCM code (the Mercosur tariff classification), CEST code, CFOP code (the operation code), unit, quantity, unit price, line amount, and the ICMS base amount, rate, and tax amount.
The invoice grand total, the products total, the discount and freight amounts, the ICMS tax base and total ICMS amount (ICMS is the Brazilian state VAT), the approximate total taxes (the Lei 12.741 transparency figure), the freight modality and carrier, and the payment method (01 cash, 03 credit card, 10 bank transfer).
The field set is modeled on the authorized NF-e document (the procNFe layout 4.00 XSD package and the Manual de Orientacao do Contribuinte). PDF only, up to 10MB and 100 pages, and the invoice is not retained after extraction.
The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.
See document data extraction if you run this for risk and compliance teams, or the extraction API if you are building it in.